{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:KS7LI3ZMMRXVON64CKO66ZDTN3","short_pith_number":"pith:KS7LI3ZM","schema_version":"1.0","canonical_sha256":"54beb46f2c646f5737dc129def64736ec13d14bf32935b2ddb47e9c5afb4f99e","source":{"kind":"arxiv","id":"2607.04055","version":1},"attestation_state":"computed","paper":{"title":"Securing Deep Learning Hardware: A Survey of Side-Channel Vulnerabilities and Countermeasures","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CR","authors_text":"Mona Hashemi, Siamak Mohammadi, Zahra Mohammadi","submitted_at":"2026-07-04T23:45:25Z","abstract_excerpt":"As deep learning models are increasingly deployed in critical sectors such as healthcare, finance, and security, ensuring their protection against emerging threats has become crucial. Among these threats, side-channel attacks (SCAs) represent a particular challenge since they can extract sensitive information such as model architectures, parameters, and even user inputs without requiring direct access to the model. By leveraging the physical and micro-architectural properties of the hardware, attackers can compromise systems. This survey begins by classifying leakage sources and attacker objec"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2607.04055","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2026-07-04T23:45:25Z","cross_cats_sorted":[],"title_canon_sha256":"3fe3c3289bd8a0b1c0d9814cd4317369bdf1dc6bd06de6a0f9201f339222267e","abstract_canon_sha256":"798e03ea7e10e33b3095440a528cbc34acf67070594bf93f9cab4fbab1e00992"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-07T02:18:55.180586Z","signature_b64":"acmMNxMVkXkGAuveGm5STQ4EA7BVKcOrwpKnEVl/ddDzmH5gLozJMhVToOUW+KQClPpgRC7RmOhGl0kRr8fyAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"54beb46f2c646f5737dc129def64736ec13d14bf32935b2ddb47e9c5afb4f99e","last_reissued_at":"2026-07-07T02:18:55.180055Z","signature_status":"signed_v1","first_computed_at":"2026-07-07T02:18:55.180055Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Securing Deep Learning Hardware: A Survey of Side-Channel Vulnerabilities and Countermeasures","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CR","authors_text":"Mona Hashemi, Siamak Mohammadi, Zahra Mohammadi","submitted_at":"2026-07-04T23:45:25Z","abstract_excerpt":"As deep learning models are increasingly deployed in critical sectors such as healthcare, finance, and security, ensuring their protection against emerging threats has become crucial. Among these threats, side-channel attacks (SCAs) represent a particular challenge since they can extract sensitive information such as model architectures, parameters, and even user inputs without requiring direct access to the model. By leveraging the physical and micro-architectural properties of the hardware, attackers can compromise systems. This survey begins by classifying leakage sources and attacker objec"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.04055","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2607.04055/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2607.04055","created_at":"2026-07-07T02:18:55.180128+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.04055v1","created_at":"2026-07-07T02:18:55.180128+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.04055","created_at":"2026-07-07T02:18:55.180128+00:00"},{"alias_kind":"pith_short_12","alias_value":"KS7LI3ZMMRXV","created_at":"2026-07-07T02:18:55.180128+00:00"},{"alias_kind":"pith_short_16","alias_value":"KS7LI3ZMMRXVON64","created_at":"2026-07-07T02:18:55.180128+00:00"},{"alias_kind":"pith_short_8","alias_value":"KS7LI3ZM","created_at":"2026-07-07T02:18:55.180128+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KS7LI3ZMMRXVON64CKO66ZDTN3","json":"https://pith.science/pith/KS7LI3ZMMRXVON64CKO66ZDTN3.json","graph_json":"https://pith.science/api/pith-number/KS7LI3ZMMRXVON64CKO66ZDTN3/graph.json","events_json":"https://pith.science/api/pith-number/KS7LI3ZMMRXVON64CKO66ZDTN3/events.json","paper":"https://pith.science/paper/KS7LI3ZM"},"agent_actions":{"view_html":"https://pith.science/pith/KS7LI3ZMMRXVON64CKO66ZDTN3","download_json":"https://pith.science/pith/KS7LI3ZMMRXVON64CKO66ZDTN3.json","view_paper":"https://pith.science/paper/KS7LI3ZM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.04055&json=true","fetch_graph":"https://pith.science/api/pith-number/KS7LI3ZMMRXVON64CKO66ZDTN3/graph.json","fetch_events":"https://pith.science/api/pith-number/KS7LI3ZMMRXVON64CKO66ZDTN3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KS7LI3ZMMRXVON64CKO66ZDTN3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KS7LI3ZMMRXVON64CKO66ZDTN3/action/storage_attestation","attest_author":"https://pith.science/pith/KS7LI3ZMMRXVON64CKO66ZDTN3/action/author_attestation","sign_citation":"https://pith.science/pith/KS7LI3ZMMRXVON64CKO66ZDTN3/action/citation_signature","submit_replication":"https://pith.science/pith/KS7LI3ZMMRXVON64CKO66ZDTN3/action/replication_record"}},"created_at":"2026-07-07T02:18:55.180128+00:00","updated_at":"2026-07-07T02:18:55.180128+00:00"}